{"id":"https://openalex.org/W2949981335","doi":"https://doi.org/10.1145/3330345.3330373","title":"GreenMM","display_name":"GreenMM","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2949981335","doi":"https://doi.org/10.1145/3330345.3330373","mag":"2949981335"},"language":"en","primary_location":{"id":"doi:10.1145/3330345.3330373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330373","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330373","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042883520","display_name":"Hadi Zamani","orcid":"https://orcid.org/0000-0002-9637-6576"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hadi Zamani","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018984473","display_name":"Yuanlai Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanlai Liu","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019585264","display_name":"Devashree Tripathy","orcid":"https://orcid.org/0000-0003-3246-6246"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devashree Tripathy","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048949780","display_name":"Laxmi N. Bhuyan","orcid":"https://orcid.org/0000-0002-8759-0458"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmi Bhuyan","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042883520"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":5.9248,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96937097,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"308","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7208530902862549},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.6557725071907043},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.595829963684082},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5550581812858582},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4930665194988251},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4875430762767792},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.48311662673950195},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4828529953956604},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4703643023967743},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.42277902364730835},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4225430488586426},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3753160238265991},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15823379158973694},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.10667973756790161},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10471442341804504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09491035342216492},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08287864923477173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7208530902862549},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6557725071907043},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.595829963684082},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5550581812858582},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4930665194988251},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4875430762767792},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.48311662673950195},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4828529953956604},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4703643023967743},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.42277902364730835},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4225430488586426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3753160238265991},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15823379158973694},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.10667973756790161},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10471442341804504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09491035342216492},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08287864923477173},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3330345.3330373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330373","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3330345.3330373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330373","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2852361309","display_name":"SHF: Small: Efficient CPU-GPU Communication for Heterogeneous Architectures","funder_award_id":"1423108","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G527974540","display_name":"SHF: Medium: Energy Efficient Computing on GPU-based Heterogeneous Systems","funder_award_id":"1513201","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7117328668","display_name":null,"funder_award_id":"CCF-1513201","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949981335.pdf","grobid_xml":"https://content.openalex.org/works/W2949981335.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1537929875","https://openalex.org/W1918863922","https://openalex.org/W1980489165","https://openalex.org/W1981384041","https://openalex.org/W1993436912","https://openalex.org/W1993508117","https://openalex.org/W1993660990","https://openalex.org/W1995746640","https://openalex.org/W2017099699","https://openalex.org/W2033597569","https://openalex.org/W2038178246","https://openalex.org/W2069238642","https://openalex.org/W2072072075","https://openalex.org/W2080592089","https://openalex.org/W2081340222","https://openalex.org/W2083613288","https://openalex.org/W2085924714","https://openalex.org/W2091067307","https://openalex.org/W2120185818","https://openalex.org/W2134380201","https://openalex.org/W2147956657","https://openalex.org/W2152211247","https://openalex.org/W2156514327","https://openalex.org/W2161125731","https://openalex.org/W2169729064","https://openalex.org/W2234633824","https://openalex.org/W2485331474","https://openalex.org/W2515526980","https://openalex.org/W2521210839","https://openalex.org/W2568810519","https://openalex.org/W2752885492","https://openalex.org/W2767694495","https://openalex.org/W2774605704","https://openalex.org/W2790957308","https://openalex.org/W2904770204","https://openalex.org/W3144807186","https://openalex.org/W4242248730","https://openalex.org/W4243624473","https://openalex.org/W4250923928","https://openalex.org/W4255592826","https://openalex.org/W4386858270"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2995605830","https://openalex.org/W2136799148","https://openalex.org/W4239424132"],"abstract_inverted_index":{"The":[0,38],"current":[1],"trend":[2],"of":[3,114],"ever-increasing":[4],"performance":[5,149],"in":[6,13,30,40,97],"scientific":[7,99],"applications":[8],"comes":[9],"with":[10,147],"tremendous":[11],"growth":[12],"energy":[14,28,57,133],"consumption.":[15],"In":[16],"this":[17,41],"paper,":[18],"we":[19,71,102,124],"present":[20],"GreenMM":[21,140],"framework":[22],"for":[23],"matrix":[24,118],"multiplication,":[25],"which":[26],"reduces":[27],"consumption":[29,134],"GPUs":[31],"through":[32],"undervolting":[33,65,115],"without":[34],"sacrificing":[35],"the":[36,46,49,60,122,126,143],"performance.":[37],"idea":[39],"paper":[42],"is":[43,135],"to":[44,54,69,80,138],"undervolt":[45],"GPU":[47],"beyond":[48],"minimum":[50],"operating":[51],"voltage":[52],"(Vmin)":[53],"save":[55],"maximum":[56],"while":[58],"keeping":[59],"frequency":[61],"constant.":[62],"Since":[63],"such":[64],"may":[66],"give":[67],"rise":[68],"faults,":[70],"design":[72],"an":[73],"Algorithm":[74],"Based":[75],"Fault":[76],"Tolerance":[77],"(ABFT)":[78],"algorithm":[79],"detect":[81],"and":[82,106,117],"correct":[83],"those":[84],"errors.":[85],"We":[86,130],"target":[87],"cuBLAS":[88],"Matrix":[89],"Multiplication":[90],"(cuBLAS-MM),":[91],"as":[92,111],"a":[93,108,112],"key":[94],"kernel":[95],"used":[96],"many":[98],"applications.":[100],"Empirically,":[101],"explore":[103],"different":[104],"errors":[105],"derive":[107],"fault":[109],"model":[110],"function":[113],"levels":[116],"sizes.":[119],"Then,":[120],"using":[121],"model,":[123],"configure":[125],"proposed":[127],"FT-cuBLAS-MM":[128],"algorithm.":[129],"show":[131],"that":[132],"reduced":[136],"up":[137],"19.8%.":[139],"also":[141],"improves":[142],"GFLOPS/Watt":[144],"by":[145],"9%":[146],"negligible":[148],"overhead.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-06-27T00:00:00"}